CN112435231A

CN112435231A - Image quality scale generation method, and method and device for evaluating image quality

Info

Publication number: CN112435231A
Application number: CN202011311993.6A
Authority: CN
Inventors: 田姣姣; 李宏铭; 庞加训
Original assignee: Shenzhen TetrasAI Technology Co Ltd
Current assignee: Shenzhen TetrasAI Technology Co Ltd
Priority date: 2020-11-20
Filing date: 2020-11-20
Publication date: 2021-03-02

Abstract

The disclosure relates to an image quality scale generation method, a method and a device for evaluating image quality, wherein the image quality scale generation method comprises the steps of obtaining a first standard image; acquiring a first objective quality index of the first standard image; determining a first subjective quality value of the first standard image according to the incidence relation between a preset objective quality index and a preset subjective quality value, and determining the first subjective quality value of the first standard image as a basic scale value; generating a rule according to the basic scale value and a preset scale value to generate a scale value sequence; acquiring a first associated image corresponding to each scale value, and generating a first image sequence, wherein for the first associated image corresponding to each scale value, a second subjective quality value of the first associated image is equal to the scale value; a first image quality scale is generated from the sequence of scale values and the first sequence of images. The present disclosure may quantify image quality in a subjective dimension.

Description

Image quality scale generation method, and method and device for evaluating image quality

Technical Field

The disclosure relates to the technical field of computer vision, in particular to an image quality scale generation method, and an image quality evaluation method and device.

Background

The image quality is influenced by various factors such as optical performance of imaging equipment, instrument noise and the like, and monitoring means can be provided for various links such as image acquisition, image processing and the like through quality evaluation. The method for evaluating the image at the present stage mainly comprises subjective evaluation and objective evaluation, wherein the evaluation results of the subjective evaluation are different due to subjective preference of an evaluator, the test results are difficult to quantify, and the consistency is difficult to guarantee; the dependence of objective evaluation on shooting conditions and labeled graph cards is high, and the applicable scenes are limited.

Disclosure of Invention

The disclosure provides an image quality scale generation method, and a method and a device for evaluating image quality.

According to an aspect of the present disclosure, there is provided a method of generating an image quality scale, the method including: acquiring a first standard image; acquiring a first objective quality index of the first standard image; determining a first subjective quality value corresponding to the first objective quality index according to the incidence relation between a preset objective quality index and a preset subjective quality value, and determining the first subjective quality value as a basic scale value; generating a scale value sequence according to the basic scale value and a preset scale value generation rule, wherein the scale value sequence comprises a plurality of scale values; acquiring a first associated image corresponding to each scale value, and generating a first image sequence, wherein for the first associated image corresponding to each scale value, a second subjective quality value of the first associated image is equal to the scale value; and generating a first image quality scale according to the scale value sequence and the first image sequence. Based on the configuration, the objective quality of the image can be quantized in the subjective perception dimension through the incidence relation between the preset objective quality index and the preset subjective quality value to obtain the subjective quality value expressing the subjective perception result, so that the image quality scale is generated, and the image quality scale accurately establishes the association between the objective quality and the subjective perception of the image, so that the image quality scale can objectively quantize the image quality in the subjective dimension.

In some possible embodiments, the obtaining the first objective quality indicator of the first standard image includes: obtaining objective parameter values, wherein the objective parameter values are used for determining the shape of an objective definition description curve; obtaining the objective definition description curve according to the objective parameter value; generating an image definition description curve corresponding to the first standard image according to the first standard image; calculating the similarity between the objective definition description curve and the image definition description curve; and if the similarity is smaller than a preset threshold value, determining the objective parameter value as a first objective quality index of the first standard image. Based on the configuration, the objective quality index capable of accurately representing the objective quality of the image can be obtained by taking the objective parameter value corresponding to the objective definition description curve as the objective quality index.

In some possible embodiments, after the calculating the similarity between the objective sharpness profile and the image sharpness profile, the method further includes: and if the similarity is greater than or equal to the preset threshold value, adjusting the objective parameter value. Based on the configuration, the objective definition description curve can be continuously adjusted to approach the image definition description curve corresponding to the first standard image, and the directivity of the first objective quality index when the objective quality of the image is reflected is improved.

In some possible embodiments, the image sharpness description curve is a modulation function transfer curve, and obtaining the objective sharpness description curve according to the objective parameter values includes: generating a description curve of the limit diffraction lens formula according to the objective parameter value and the lens formula of the limit diffraction lens; the objective parameter value represents the pixel resolution capability of the camera equipment; determining a description curve of the extreme diffraction lens formula as the objective definition description curve. Based on the configuration, the effect that the objective definition description curve approaches the image definition description curve corresponding to the first standard image can be improved by selecting a proper objective definition description curve, so that the accuracy of the first objective quality index is improved.

In some possible embodiments, the obtaining the first associated image corresponding to each scale value includes: acquiring an image processing parameter for each scale value; processing the first standard image according to the image processing parameters to obtain a processed image; acquiring a second objective quality index of the processed image; determining a second subjective quality value corresponding to the second objective quality index according to the incidence relation; and if the second subjective quality value is equal to the scale value, determining the processed image as a first associated image corresponding to the scale value. Based on the configuration, the first associated image with the second subjective quality value equal to the scale value is obtained, and therefore the corresponding relation between the first associated image and the scale value is established.

In some possible embodiments, after the determining, according to the association relationship, a second subjective quality value corresponding to the second objective quality indicator, the method further includes: and if the second subjective quality value of the processed image is not equal to the scale value, adjusting the image processing parameter. Based on the above configuration, the first related image can be obtained by continuously adjusting the image processing parameters.

In some possible embodiments, after the determining the processed image as the first associated image corresponding to the scale value, the method further includes: and recording the corresponding relation between the scale value and the image processing parameter. Based on the above configuration, it is possible to increase the image quality scale generation speed by saving the correspondence relationship between the scale values and the image processing parameters so that the corresponding image quality scale can be generated on the basis of other standard images on the basis of the same principle without going through the step of constantly adjusting the image processing parameters again.

In some possible embodiments, after the recording the correspondence of the scale values to the image processing parameters, the method further comprises: acquiring a second standard image; acquiring the scale value sequence; processing the second standard image according to the corresponding relation between the scale value and the image processing parameter aiming at each scale value in the scale value sequence to obtain a second associated image corresponding to the scale value; generating a second image sequence according to a second associated image corresponding to each scale value in the scale value sequence; and generating a second image quality scale according to the scale value sequence and the second image sequence. Based on the above configuration, it is possible to quickly generate another image quality scale by changing the standard image and then using the already obtained image processing parameters.

According to a second aspect of the present disclosure, there is provided a method of evaluating image quality based on an image quality scale, the method comprising: acquiring an image to be evaluated; acquiring an image quality scale; determining a target image with the highest quality similarity with the image to be evaluated from a plurality of images included by the image quality scale; determining a target scale value corresponding to the target image as an evaluation result of the image to be evaluated based on a plurality of scale values included by the image quality scale; the image quality scale is obtained according to the method for generating the image quality scale in any one of the first aspect. Based on the configuration, the target image with the quality most similar to that of the image to be evaluated in the image quality scale is selected, and the scale value of the target image is used as the evaluation result of the image to be evaluated, so that a uniform standard is established for image quality evaluation, an evaluator can rely on the evaluation process, the influence of the subjective intention of the evaluator on the evaluation result is reduced, the evaluation result is more accurate and stable, and the subjective feeling of the evaluator is consistent.

In some possible embodiments, the determining, from the plurality of images included in the image quality scale, a target image with the highest quality similarity to the image to be evaluated includes: displaying the image to be evaluated; displaying each image in the target image quality scale; and in response to an operation instruction of a user, determining a selected image in the target image quality scale, and taking the selected image as the target image. Based on the configuration, each image of the image quality scale and the image to be evaluated can be displayed for the evaluator, and the evaluator selects the target image with the most similar quality, so that the evaluation is convenient for the evaluator, the evaluation efficiency is improved, and the burden of the evaluator is reduced.

According to a third aspect of the present disclosure, there is provided an apparatus for generating an image quality scale, the apparatus comprising: the first standard image acquisition module is used for acquiring a first standard image; the objective quality index acquisition module is used for acquiring a first objective quality index of the first standard image; the subjective quality value acquisition module is used for determining a first subjective quality value corresponding to the first objective quality index according to the incidence relation between a preset objective quality index and a preset subjective quality value, and determining the first subjective quality value as a basic scale value; the scale value sequence generating module is used for generating a scale value sequence according to the basic scale value and a preset scale value generating rule, wherein the scale value sequence comprises a plurality of scale values; a first image sequence generation module, configured to obtain a first associated image corresponding to each scale value, and generate a first image sequence, where for the first associated image corresponding to each scale value, a second subjective quality value of the first associated image is equal to the scale value; and the first image quality scale generating module is used for generating a first image quality scale according to the scale value sequence and the first image sequence.

In some possible embodiments, the objective quality indicator obtaining module includes: an objective parameter value obtaining unit, configured to obtain an objective parameter value, where the objective parameter value is used to determine a shape of an objective sharpness description curve; the objective definition description curve acquisition unit is used for acquiring the objective definition description curve according to the objective parameter value; the image definition description curve generating unit is used for generating an image definition description curve corresponding to the first standard image according to the first standard image; the similarity calculation unit is used for calculating the similarity between the objective definition description curve and the image definition description curve; and the objective quality index determining unit is used for determining the objective parameter value as a first objective quality index of the first standard image if the similarity is smaller than a preset threshold value.

In some possible embodiments, the objective quality indicator obtaining module is further configured to adjust the objective parameter value if the similarity is greater than or equal to the preset threshold.

In some possible embodiments, the image sharpness description curve is a modulation function transfer curve, and the objective sharpness description curve obtaining unit is further configured to generate a description curve of the extreme diffraction lens formula according to the objective parameter value and the lens formula of the extreme diffraction lens; the objective parameter value represents the pixel resolution capability of the camera equipment; determining a description curve of the extreme diffraction lens formula as the objective definition description curve.

In some possible embodiments, the first image sequence generation module is configured to obtain an image processing parameter for each of the scale values; processing the first standard image according to the image processing parameters to obtain a processed image; acquiring a second objective quality index of the processed image; determining a second subjective quality value corresponding to the second objective quality index according to the incidence relation; and if the second subjective quality value is equal to the scale value, determining the processed image as a first associated image corresponding to the scale value.

In some possible embodiments, the first image sequence generation module is further configured to adjust the image processing parameter if the second subjective quality value of the processed image is not equal to the scale value.

In some possible embodiments, the first image sequence generation module is further configured to record a correspondence between the scale value and the image processing parameter.

In some possible embodiments, the apparatus is further configured to acquire a second standard image; acquiring the scale value sequence; processing the second standard image according to the corresponding relation between the scale value and the image processing parameter aiming at each scale value in the scale value sequence to obtain a second associated image corresponding to the scale value; generating a second image sequence according to a second associated image corresponding to each scale value in the scale value sequence; and generating a second image quality scale according to the scale value sequence and the second image sequence.

According to a fourth aspect of the present disclosure, there is provided an apparatus for evaluating image quality based on an image quality scale, the apparatus including: the image to be evaluated acquisition module is used for acquiring an image to be evaluated; the image quality scale acquisition module is used for acquiring an image quality scale; the target image determining module is used for determining a target image with the highest quality similarity with the image to be evaluated from a plurality of images included in the image quality scale; the evaluation result output module is used for determining a target scale value corresponding to the target image as an evaluation result of the image to be evaluated based on a plurality of scale values included by the image quality scale; the image quality scale is obtained according to the method for generating the image quality scale in any one of the first aspect.

In some possible embodiments, the target image determination module is further configured to display the image to be evaluated; displaying each image in the target image quality scale; and in response to an operation instruction of a user, determining a selected image in the target image quality scale, and taking the selected image as the target image.

According to a fifth aspect of the present disclosure, there is provided an electronic device comprising at least one processor, and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the at least one processor implements a method of generating an image quality scale according to any one of the first aspect or a method of evaluating image quality based on an image quality scale according to any one of the second aspect by executing the instructions stored by the memory.

According to a sixth aspect of the present disclosure, there is provided a computer-readable storage medium having at least one instruction or at least one program stored therein, the at least one instruction or the at least one program being loaded by and executed by a processor to implement the method for generating an image quality scale according to any one of the first aspects or the method for evaluating image quality based on the image quality scale according to any one of the second aspects.

In the embodiment of the disclosure, the image quality scale can quantify objective image quality in the dimension of subjective feeling by establishing the relation between the objective quality index and the subjective quality value, so that the subjective evaluation result obtained by evaluation based on the image quality scale is objective and fair, and the dependence on an evaluator is reduced.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Other features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.

Drawings

In order to more clearly illustrate the embodiments of the present specification or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present specification, and other drawings can be obtained by those skilled in the art without inventive efforts.

Fig. 1 shows a flow chart of a method of generating an image quality scale according to an embodiment of the present disclosure;

fig. 2 illustrates a schematic diagram of a first standard image obtained by shooting original images of an ISO12233 standard test card according to an embodiment of the disclosure;

FIG. 3 is a flowchart illustrating obtaining a first objective quality indicator of the first standard image according to an embodiment of the disclosure;

fig. 4 is a flowchart illustrating an image sharpness description curve corresponding to the first standard image according to an embodiment of the disclosure;

FIG. 5 illustrates a flow chart for calculating a region sharpness profile for each of the calculated regions in accordance with an embodiment of the present disclosure;

FIG. 6 illustrates ESF curves for a row in a computing area, according to an embodiment of the disclosure;

FIG. 7 illustrates a corresponding LSF curve for a row in a computing region according to an embodiment of the disclosure;

FIG. 8 illustrates a corresponding SFR curve for a row in a computing region, in accordance with an embodiment of the present disclosure;

FIG. 9 is a flowchart illustrating a method for obtaining a first correlation image corresponding to each of the scale values according to an embodiment of the disclosure;

FIG. 10 shows a schematic diagram of one of the first image quality scales according to an embodiment of the present disclosure;

FIG. 11 shows a flow diagram of a method of generating a second scale of image quality according to an embodiment of the disclosure;

FIG. 12 shows a schematic diagram of one of the second standard images according to an embodiment of the present disclosure;

FIG. 13 illustrates a schematic diagram of generating a second associated image according to an embodiment of the present disclosure;

FIG. 14 shows a flow diagram of a method of evaluating image quality based on an image quality scale;

FIG. 15 shows a flowchart of method step S30-1 for evaluating image quality based on an image quality scale according to an embodiment of the present disclosure;

FIG. 16 shows a schematic diagram of an evaluation report according to an embodiment of the present disclosure;

fig. 17 shows a block diagram of an image quality scale generation apparatus according to an embodiment of the present disclosure;

FIG. 18 shows a block diagram of an apparatus for evaluating image quality based on an image quality scale according to an embodiment of the present disclosure;

FIG. 19 shows a block diagram of an electronic device in accordance with an embodiment of the disclosure;

fig. 20 shows a block diagram of another electronic device in accordance with an embodiment of the disclosure.

Detailed Description

The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments in the present description, belong to the protection scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.

The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.

The term "and/or" herein is merely an association describing an associated object, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.

Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present disclosure. It will be understood by those skilled in the art that the present disclosure may be practiced without some of these specific details. In some instances, methods, means, elements and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present disclosure.

In the related technology for evaluating the image quality, the subjective evaluation still occupies a high proportion, the subjective evaluation result is greatly influenced by subjective factors of an evaluator and is difficult to quantify, and the consistency of the subjective evaluation result is difficult to guarantee, for example, the evaluator A considers the quality to be high, and the evaluator B considers the quality to be common, so that the subjective evaluation result is possibly unstable. The method comprises the steps of obtaining an objective quality index of an image, and quantifying the objective quality index on a subjective perception dimension to obtain a subjective quality value representing a subjective perception result, wherein the obtaining process of the subjective quality value is irrelevant to an evaluator, the image quality scale constructed according to the obtained subjective quality value is also irrelevant to the evaluator, and the process of evaluating the image quality by using the image quality scale can reduce the dependence on the evaluator, so that the subjective evaluation result is objective and fair, and the subjective evaluation result has better consistency and stability.

On the basis of obtaining the image quality scale, the disclosure can further show a scheme for evaluating the image quality based on the image quality scale, by comparing the image to be evaluated with each image in the image quality scale, a target image with the quality closest to the quality of the image to be evaluated can be selected, and a subjective evaluation result of the image to be evaluated is obtained according to the subjective quality value of the target image. By means of the image quality scale, the subjective evaluation result of the image to be evaluated can be consistent, and the influence of the subjective intention of an evaluator on the evaluation result is reduced as much as possible. The quality evaluation result obtained by the scheme disclosed by the disclosure is accurate and reliable, and can be widely applied to evaluating the image pickup quality of various image pickup devices, so that a reliable basis is provided for the evaluation and optimization of the image pickup devices.

The method and the device can be applied to evaluation of various quality dimensions of the image, such as image definition, image chromaticity, image contrast and the like, and the method and the device are not limited in the embodiment of the disclosure.

Any one of the method for generating the image quality scale or the method for evaluating the image quality based on the image quality scale provided by the embodiment of the present disclosure may be executed by a terminal device, a server, or other types of electronic devices, where the terminal device may be a User Equipment (UE), a mobile device, a User terminal, a Personal Digital Assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, or the like. In some possible implementations, any one of the method for generating the image quality scale or the method for evaluating the image quality based on the image quality scale can be implemented by the processor calling the computer readable instructions stored in the memory. The following describes a method for generating an image quality scale and a method for evaluating image quality based on the image quality scale according to an embodiment of the present disclosure, taking an electronic device as an execution subject. The method for generating the image quality scale and the method for evaluating the image quality based on the image quality scale are realized by calling computer readable instructions stored in a memory through a processor.

Fig. 1 shows a flowchart of a method for generating an image quality scale according to an embodiment of the present disclosure, and as shown in fig. 1, the method includes:

s10: a first standard image is acquired.

The first standard image is a reference for generating an image quality scale based on which the other images in the image quality scale are obtained, and is considered to have the highest image quality.

Taking an image quality scale for evaluating the sharpness as an example, the first standard image is an image with the highest sharpness. According to the method and the device, the shooting object can be shot by using the actually-obtained camera equipment with the highest image shooting capability, and the shooting object is a drawing card meeting international standards or a drawing board set up in a laboratory. For example, in the present disclosure, an image capturing apparatus with the highest image capturing capability may be used to capture the original image of the ISO12233 standard test card, so as to obtain a first standard image including the original image. As shown in fig. 2, a schematic diagram of a first standard image obtained by shooting the original image of the ISO12233 standard test card is shown.

In some embodiments, the shooting condition of the first standard image may be determined before the first standard image is acquired, and the shooting condition may be used as a generation condition of an image quality scale obtained based on the first standard image. The above shooting conditions can also be used as the using conditions of the image quality scale, namely when the image scale is used, the image quality scale which is the same as the shooting conditions of the image to be evaluated is selected to evaluate the quality of the image to be evaluated, so that the image scale can be constrained to be generated and used on the basis of the same shooting conditions, errors caused by different shooting conditions in the evaluation process of the image to be evaluated can be avoided, and the evaluation accuracy is improved.

In some embodiments, each image quality scale may have its uniquely determined capture condition under which it was generated and is also used. The generation scene and the use scene of the image quality scale can be determined by limiting the shooting conditions, and the normalization and the accuracy of the image quality scale are improved. The shooting conditions may include lighting conditions and shooting environments, and the embodiment of the present disclosure does not limit specific contents of the shooting conditions. For example, it may be required that the lux (illumination unit) of the shooting condition is 2, and the shooting environment satisfies the brightness uniformity.

In some embodiments, the generation and use of the image quality scale may both be related to the shooting conditions, and the image quality scale corresponding to the changed shooting conditions may be acquired by changing the shooting conditions, so that the implementation of the present disclosure is not particularly limited by the shooting conditions. For example, a shooting condition corresponding to an actual image quality evaluation environment can be obtained, an image quality scale suitable for the shooting condition is generated, then an image to be evaluated is obtained in the actual evaluation environment, and the image to be evaluated is evaluated according to the image quality scale.

S20: and acquiring a first objective quality index of the first standard image.

The first objective quality index in the present disclosure may be related to a dimension for evaluating image quality, for example, if the image quality is evaluated in a definition dimension, the first objective quality index may be a definition index; if the image quality evaluation is performed in the contrast dimension, the first objective quality index may be a contrast index.

For image quality evaluation in the definition dimension, as shown in fig. 3, a flowchart for obtaining a first objective quality indicator of the first standard image according to an embodiment of the disclosure is shown, and includes:

s21, objective parameter values are obtained, and the objective parameter values are used for determining the shape of the objective definition description curve.

And S22, obtaining the objective definition description curve according to the objective parameter values.

And S23, generating an image definition description curve corresponding to the first standard image according to the first standard image.

As shown in fig. 4, the generating of the image definition description curve corresponding to the first standard image according to the embodiment of the disclosure includes:

at least one calculation region is determined in the first standard image S231.

Taking the shooting result of fig. 2 as an example, a corresponding calculation region can be framed at the position of any one of the oblique sides. Selecting at least one oblique side in the first standard image; for any one of the hypotenuses, a calculation region is boxed such that only the one hypotenuse is included in the calculation region.

For example, one oblique side may be selected on each of the left and right sides in fig. 2, and two oblique sides may be selected in the middle, with the selection results for the oblique sides being indicated by arrows in fig. 2. For each selected hypotenuse, a unique calculation region may be determined that includes only a portion of the hypotenuse.

And S232, calculating the region definition description curve of each calculation region.

As shown in fig. 5, which shows a flowchart for calculating a region definition description curve of each of the calculation regions according to an embodiment of the present disclosure, includes:

s2321, calculating a line definition description curve corresponding to each line in the calculation region.

For example, the line definition description curve may be an Edge Spread Function (ESF) curve, and for each line of the calculation region, a corresponding ESF curve may be generated. As shown in fig. 6, which illustrates an ESF curve corresponding to a row in a computing area according to an embodiment of the present disclosure. The abscissa of the curve represents the pixel position of the certain row, and the ordinate of the curve represents the gray value or the brightness value corresponding to the pixel position of the certain row.

In some embodiments, the Line definition description curve may also be a Line Spread Function (LSF) curve, which may be derived from an ESF curve. As shown in fig. 7, which illustrates LSF curves corresponding to a certain row in a computation region according to an embodiment of the present disclosure. The abscissa of the curve represents the pixel position of the certain row, and the ordinate of the curve represents the gray value or the brightness value corresponding to the pixel position of the certain row.

In some embodiments, the line definition description curve may also be a Spatial Frequency Response (SFR) curve, which may be obtained by fourier transformation of an LSF curve. As shown in fig. 8, which illustrates a SFR curve corresponding to a row in a computing region according to an embodiment of the disclosure. The abscissa of the curve represents frequency and the ordinate of the curve represents spatial frequency response.

S2322, oversampling is carried out on the line definition description curves corresponding to the lines in the calculation region, and the region definition description curve of the calculation region is obtained.

For example, the region definition description curve may be expressed as a Modulation Transfer Function (MTF) curve, which may be obtained by performing oversampling on the line definition description curve corresponding to each line. For example, oversampling is performed on the SFR curves corresponding to each row.

And S233, determining the image definition description curve corresponding to the first standard image according to the definition description curves of the areas.

The present disclosure does not limit a specific method for determining the image definition description curve corresponding to the first standard image according to each of the region definition description curves.

For example, the sharpness description curves of the regions may be directly summed to obtain the sharpness description curve of the image, or the sharpness description curves of the regions may be weighted and summed to obtain the sharpness description curve of the image, where the weight may be related to a specific position of the calculation region, for example, the calculation region located in the middle region of the first standard image corresponds to a higher weight, and the calculation region located in the edge region of the first standard image corresponds to a lower weight.

And S24, calculating the similarity between the objective definition description curve and the image definition description curve.

In the embodiment of the disclosure, the objective definition description curve may be used to approximate the image definition description curve corresponding to the first standard image. In some embodiments, the image definition description curve corresponding to the first standard image may be a Modulation Transfer Function (MTF) curve, and since the MTF curve is similar to the description curve of the limit diffraction lens formula, the description curve of the limit diffraction lens formula may be selected as the objective definition description curve, that is, the description curve of the limit diffraction lens formula may be generated according to the objective parameter value and the lens formula of the limit diffraction lens; the objective parameter value represents the capacity of the image pickup equipment for resolving pixels in a lens formula of the limit diffraction lens; the description curve of the above-described extreme diffraction lens formula is determined as the above-described objective definition description curve. According to the embodiment of the disclosure, the effect that the objective definition description curve approaches the image definition description curve corresponding to the first standard image can be improved by selecting the appropriate objective definition description curve, so that the accuracy of the first objective quality index is improved.

Specifically, the extreme diffraction lens is formulated as

Wherein v, m (v) respectively represent frequency and spatial frequency responses, which can be used as independent variable and dependent variable of the formula, and k uniquely determining the shape of the curve corresponding to the extreme diffraction lens formula is an objective parameter value.

And S25, if the similarity is smaller than a preset threshold, determining the objective parameter value as a first objective quality index of the first standard image.

If the similarity is greater than or equal to the preset threshold, the objective parameter value is adjusted, then an objective definition description curve can be obtained according to the adjusted objective parameter value, step S24 is repeatedly executed until the calculated similarity is less than the preset threshold, and the adjusted objective parameter value can be determined as the first objective quality index. According to the embodiment of the disclosure, the objective definition description curve can be continuously adjusted to approach the image definition description curve corresponding to the first standard image, so that the directivity of the first objective quality index when the objective quality of the first standard image is reflected is improved.

S30: and determining a first subjective quality value corresponding to the first objective quality index according to the incidence relation between the preset objective quality index and the preset subjective quality value, and determining the first subjective quality value as a basic scale value.

In the disclosure, the incidence relation between the preset objective quality index and the preset subjective quality value is a bridge for correlating the objective quality index and the subjective quality value, wherein the objective quality index reflects an objective evaluation result of an image, the objective quality evaluation result does not transfer from the intention of an evaluator, and the subjective quality value reflects the subjective feeling of the image. The incidence relation can quantify the objective quality index on the subjective perception dimension to obtain a subjective quality value capable of reflecting the subjective feeling of the user. In order to enable the subjective quality value to accurately reflect the subjective feeling of the user, the association relation can also be obtained based on an authoritative subjective perception quantification model. Although the subjective quality value is a subjective evaluation result, the subjective quality value is based on an objective quality index reflecting the result of objective quality evaluation, so that the acquisition process of the subjective quality value does not transfer the intention of an evaluator, and the subjective quality value and the objective quality index have strong correlation, thereby ensuring that the subjective quality value not only accurately reflects the objective quality of an image, but also unifies the objective quality of the image with the subjective feeling of a person, and leading the subjective evaluation result to be consistent with the objective evaluation result.

Different objective quality indexes and the incidence relation between the preset objective quality indexes and the preset subjective quality value can be obtained through quality evaluation of different dimensions. For example, if the image quality scale is mainly used for evaluating image quality from a definition dimension, the objective quality index may be objective definition, and the association relationship between the preset objective quality index and the preset subjective quality value may describe the association between the objective definition and the subjective quality value of the image. If the image quality scale is mainly used for evaluating the image quality from the contrast dimension, the objective quality value index can be objective contrast, and the association relationship between the preset objective quality index and the preset subjective quality value can describe the association between the objective contrast and the subjective quality value of the image.

Illustratively, taking the evaluation of image quality from the sharpness dimension as an example, the Standard Quality Specification (SQS) mentioned in the standard ISO20462-3 may be used₂) Describing the correlation between the preset objective quality index and the preset subjective quality value, the SQS₂) Is expressed as

Wherein k can be the visitor quality index, SQS₂The value of (d) may be taken as a subjective quality value.

Illustratively, in some embodiments, the SQS may be₂Is approximated as the JND value, and the calculated SQS is used₂And directly outputting the value as JND to obtain a subjective quality value expressed in the form of JND.

In this disclosure, step S20 may obtain a first objective quality indicator of the first standard image, where the first objective image indicator reflects a result of objective quality evaluation of the first standard image, and the first subjective quality value obtained according to the association between the preset objective quality indicator and the preset subjective quality value reflects subjective feeling of the first standard image.

S40: and generating a scale value sequence according to the basic scale value and a preset scale value generation rule, wherein the scale value sequence comprises a plurality of scale values.

The present disclosure does not limit the specific contents of the scale value generation rule.

For example, the scale value generation rule may form an arithmetic series or an geometric series for scale values of the scale value sequence, for example, if the basic scale value is 33JND (Just noticeable difference), the tolerance of the arithmetic series is 3, and then the scale values in the scale value sequence may be 33JND, 30JND,27JND,24JND,21JND, and so on.

For example, the scale value generation rule may further set a difference value sequence, and the scale value sequence may be generated according to the difference value sequence and the base scale value. For example, the difference sequence may be 5,4,3,2, and the base scale value is 33JND, and the scale values in the scale value sequence may be 33JND, 28JND, 24JND,21JND, and 19JND in sequence.

In some embodiments, the lower limit of the scale value may be determined based on the dimension of the evaluation. Taking the sharpness evaluation as an example, when the scale value is too low, the significance of performing the sharpness evaluation of the image is not great because the image is already very blurred. In such a scenario, a lower limit of a scale value may be defined, and when a scale value sequence is generated, if the generated scale value is smaller than the lower limit of the scale value, no subsequent scale value is generated. Illustratively, if the reference scale value is 33JND, the lower limit threshold of the scale value is 15, and the tolerance of the arithmetic progression is 3, the scale values in the scale value sequence thus obtained are 33JND, 30JND,27JND,24JND,21JND,18JND, and 15JND in this order.

S50: and acquiring a first associated image corresponding to each scale value, and generating a first image sequence, wherein for the first associated image corresponding to each scale value, a second subjective quality value of the first associated image is equal to the scale value.

After the scale value sequence is determined, for each scale value except for the basic scale value in the scale value sequence, the quality of the first standard image can be reduced by performing image processing on the first standard image, and a first associated image with a second subjective quality value equal to each scale value is obtained.

As shown in fig. 9, which shows a flowchart of acquiring a first associated image corresponding to each of the scale values according to an embodiment of the present disclosure, the acquiring a first associated image corresponding to each of the scale values includes:

s51: and acquiring an image processing parameter aiming at each scale value.

S52: and processing the first standard image according to the image processing parameters to obtain a processed image.

S53: and acquiring a second objective quality index of the processed image.

The method for obtaining the second objective quality index of the processed image in step S53 is the same as the method for obtaining the first objective quality index of the first standard image in step S20, and is not repeated herein.

S54: and determining a second subjective quality value of the processed image according to the association relation.

S55: and if the second subjective quality value of the processed image is equal to the scale value, determining the processed image as a first related image corresponding to the scale value.

If the second subjective quality value of the processed image is not equal to the scale value, the image processing parameter is adjusted, and then the first standard image can be processed according to the adjusted image processing parameter to obtain a processed image. Step S53 is repeatedly executed until the second subjective quality value of the processed image is equal to the scale value, so that the first related image corresponding to the scale value can be determined. The embodiment of the disclosure can obtain the first associated image by continuously adjusting the image processing parameters, thereby establishing the corresponding relationship between the first associated image and the scale value.

For example, if the image quality scale is mainly used for evaluating image quality from a definition dimension, the basic scale value is 33JND, and a scale value in the scale value sequence is 24JND, the first standard image may be blurred, so that the second subjective quality value of the blurred image is 24JND, and the blurred image is determined as a first related image corresponding to the scale value 24 JND.

In some embodiments, after the processed image is determined as the first related image corresponding to the scale value, the correspondence between the scale value and the image processing parameter may be recorded. By storing the corresponding relationship between the scale values and the image processing parameters, other image quality scales can be generated quickly based on other standard images. The corresponding relation between the scale values and the image processing parameters can be saved, so that the corresponding image quality scale can be generated on the basis of other standard images based on the same principle without going through the step of continuously adjusting the image processing parameters again, and the image quality scale generation speed is improved.

S60: and generating a first image quality scale according to the scale value sequence and the first image sequence.

Illustratively, if the scale values in the scale value sequence are 33JND, 30JND,27JND,24JND,21JND,18JND and 15JND in sequence, wherein 33JND is a basic scale value; accordingly, the first image sequence includes 7 images, and the corresponding images have a scale value of 33JND, 30JND,27JND,24JND,21JND,18JND, and 15JND, respectively, wherein the image having the scale value of 33JND is the first standard image. As shown in fig. 10, which shows a schematic diagram of one of the first image quality scales according to an embodiment of the present disclosure. The individual pictures in fig. 10, which constitute a scale capable of image quality evaluation in the sharpness dimension, are arranged in ascending order of JND.

According to the image quality measuring method and device, the objective quality of the image can be quantized in the subjective perception dimension through the incidence relation between the preset objective quality index and the preset subjective quality value, the first subjective quality value and the second subjective quality value expressing the subjective perception result are obtained, and therefore the first image quality scale is generated, the first image quality scale accurately establishes the incidence of the objective quality and the subjective perception of the image, and the first image quality scale can objectively quantize the image quality in the subjective dimension.

The embodiment of the present disclosure may further generate a second quality scale based on a second standard image different from the first standard image according to a correspondence relationship between the scale values and the image processing parameters recorded in advance. The second standard image may be any standard image obtained based on the same photographing conditions as the first standard image.

As shown in fig. 11, which shows a flowchart of a method for generating a second image quality scale according to an embodiment of the present disclosure, the method includes:

s100, acquiring a second standard image.

As shown in fig. 12, a schematic diagram of one of the second standard images according to an embodiment of the present disclosure is shown. The second standard image is obtained by photographing the drawing board built based on the laboratory under the same photographing condition as the first standard image. The second standard image is different from the subject of the first standard image, but the shooting conditions are the same.

S200, acquiring the scale value sequence.

S300, processing the second standard image according to the corresponding relation between the scale values and the image processing parameters aiming at each scale value in the scale value sequence to obtain a second associated image corresponding to the scale value.

Illustratively, in the process of generating an image quality scale for evaluating image quality from a definition dimension based on a first standard image, if a base scale value corresponding to the first standard image is 33JND, other scale values in a scale value sequence are 28JND,23JND,18JND and 13JND in sequence; the blurring processing parameters corresponding to the other scale values are M1, M2, M3, and M4, and thus when an image quality scale for evaluating the image quality from the sharpness dimension is generated based on the second standard image, the basic scale value corresponding to the second standard image can be directly considered to be 33JND, and the blurring processing is performed on the second standard image based on the blurring processing parameters M1, M2, M3, and M4, so that the obtained image is the second related image with the corresponding scale values of 28JND,23JND,18JND, and 13 JND.

As shown in fig. 13, a schematic diagram of generating a second associated image according to an embodiment of the present disclosure is shown. The second related image on the left side is the second standard image on the right side and is obtained through blurring processing.

S400, generating a second image sequence according to a second associated image corresponding to each scale value in the scale value sequence.

S500, generating a second image quality scale according to the scale value sequence and the second image sequence.

In some embodiments, the image quality scale corresponding to the shooting condition may be obtained by changing the shooting condition, and the process of obtaining the quality scale is as described above and is not described herein again.

The definition dimension is taken as an example in the present disclosure, the generation process of the image quality scale is described, and the image quality scales of other dimensions are not repeated.

Based on the configuration, the present disclosure shows a method for generating an image quality scale, where the image quality scale accurately establishes the association between the objective quality and the subjective perception of an image through the association relationship between the preset objective quality index and the preset subjective quality value, so that the image quality scale can quantify the objective image quality in the subjective dimension. The generation process of the image quality scale is objective, so that the generation of the image quality scale does not depend on subjective factors, but the subjective evaluation result can be stably quantified. The evaluation of the image to be evaluated based on the image quality scale can also enable the evaluation result to be accurate and stable, and even if different evaluators are used, the evaluation result can also be enabled to have consistency.

Fig. 14 shows a flowchart of a method for evaluating image quality based on an image quality scale according to an embodiment of the present disclosure, the method comprising:

and S10-1, acquiring the image to be evaluated.

In some embodiments, in order to evaluate the image capturing quality of the image capturing apparatus, the capturing condition may be determined first. For example, there are two image quality scales corresponding to the existing shooting condition 1, which are scale 1 and scale 2 respectively; if there are two image quality scales corresponding to the photographing condition 2, namely, the scale 3 and the scale 4, and there is no corresponding image quality scale under other photographing conditions, any one of the photographing condition 1 and the photographing condition 2 can be used as the photographing condition of the image to be evaluated.

In some embodiments, a photographic subject may also be determined. For example, the shooting condition 1 is selected as the shooting condition of the image to be evaluated, and the shooting object corresponding to the scale 1 is selected as the shooting object of the image to be evaluated. And under the shooting condition, shooting the shooting object by using the shooting equipment to obtain the image to be evaluated.

S20-1, acquiring an image quality scale.

In some embodiments, if the image to be evaluated is obtained, the target image quality scale may be determined according to the shooting condition of the image to be evaluated and the shooting object. For example, the image to be evaluated is obtained by shooting a drawing board set up in a laboratory under the condition of 2 lux. The standard image corresponding to the reference scale value in the image quality scale can also be obtained by shooting a drawing board built in a laboratory under the condition that lux is 2, and the image quality scale is selected according to the shooting condition and the shooting object of the image to be evaluated, so that errors caused by the fact that the image to be evaluated and the shooting condition or the shooting object of the image quality scale are different in the image evaluation process are avoided.

The method for generating the image quality scale used in this step has been described above, and is not described again here.

And S30-1, determining a target image with the highest quality similarity with the image to be evaluated from a plurality of images included in the image quality scale.

In the actual evaluation process, each image of the image quality scale and the image to be evaluated can be displayed for an evaluator, and the evaluator selects a target image which is most similar to the image to be evaluated in the image quality scale; or the machine respectively carries out quality similarity matching on each image of the image quality scale and the image to be evaluated, and the image with the highest matching degree is taken as a target image.

In the present disclosure, the quality similarity is related to an evaluation dimension, for example, if quality evaluation is performed in a definition dimension, the quality similarity may be the definition similarity; if quality evaluation is performed in the contrast dimension, the quality similarity may be the contrast similarity.

In some embodiments, the selection of the target image may be made dependent on the evaluator. As shown in fig. 15, which shows a flowchart of step S30-1 of a method for evaluating image quality based on an image quality scale according to an embodiment of the present disclosure, where the determining a target image with the highest quality similarity to the image to be evaluated includes:

s31-1, displaying the image to be evaluated;

s32-1, displaying each image in the target image quality scale;

and S33-1, in response to the operation instruction of the user, determining the selected image in the target image quality scale, and taking the selected image as the target image.

And S40-1, determining the target scale value corresponding to the target image as the evaluation result of the image to be evaluated based on a plurality of scale values included by the image quality scale.

The method and the device can display each image of the image quality scale and the image to be evaluated for the evaluator, and the evaluator selects the target image with the most similar quality, so that the evaluation is facilitated, the evaluation efficiency is improved, and the burden of the evaluator is reduced.

In some embodiments, an evaluation report may be generated according to the evaluation result, and the evaluation report may include the shooting condition and the evaluation result. Further, the evaluation report can also comprise evaluation time, evaluation persons and equipment participating in evaluation. As shown in fig. 16, which shows a schematic diagram of an evaluation report according to an embodiment of the present disclosure, the evaluation report shows evaluation results of images captured by devices involved in evaluation under four capturing conditions, and when lux is 0, the evaluation result is JND 0; when lux is 2, the evaluation result is JND 27; when lux is 7, the evaluation result is JND 0; when lux is 14, the evaluation result is JND 24.

According to the method for evaluating the image quality based on the image quality scale, the target image which is most similar to the image to be evaluated in the image quality scale is selected, the scale value of the target image is used as the evaluation result of the image to be evaluated, and therefore a uniform standard is established for image quality evaluation, an evaluator can rely on the target image in the evaluation process, the influence of the subjective will of the evaluator on the evaluation result is reduced, the evaluation result is more accurate and stable, and the subjective feeling of the evaluator is consistent.

It will be understood by those skilled in the art that in the method of the present invention, the order of writing the steps does not imply a strict order of execution and any limitations on the implementation, and the specific order of execution of the steps should be determined by their function and possible inherent logic.

It is understood that the above-mentioned method embodiments of the present disclosure can be combined with each other to form a combined embodiment without departing from the logic of the principle, which is limited by the space, and the detailed description of the present disclosure is omitted.

Fig. 17 shows a block diagram of an image quality scale generation apparatus according to an embodiment of the present disclosure; as shown in fig. 17, the above apparatus includes:

a first standard image obtaining module 10, configured to obtain a first standard image;

an objective quality index obtaining module 20, configured to obtain a first objective quality index of the first standard image;

a subjective quality value obtaining module 30, configured to determine, according to an association relationship between a preset objective quality index and a preset subjective quality value, a first subjective quality value corresponding to the first objective quality index, and determine the first subjective quality value as a basic scale value;

a scale value sequence generating module 40, configured to generate a scale value sequence according to the basic scale value and a preset scale value generating rule, where the scale value sequence includes multiple scale values;

a first image sequence generating module 50, configured to obtain a first associated image corresponding to each scale value, and generate a first image sequence, where for the first associated image corresponding to each scale value, a second subjective quality value of the first associated image is equal to the scale value;

a first image quality scale generating module 60, configured to generate a first image quality scale according to the scale value sequence and the first image sequence.

In some possible embodiments, the objective quality indicator obtaining module includes: an objective parameter value obtaining unit, configured to obtain an objective parameter value, where the objective parameter value is used to determine a shape of an objective sharpness description curve; an objective definition description curve obtaining unit, configured to obtain the objective definition description curve according to the objective parameter value; an image definition description curve generating unit, configured to generate an image definition description curve corresponding to the first standard image according to the first standard image; the similarity calculation unit is used for calculating the similarity between the objective definition description curve and the image definition description curve; and the objective quality index determining unit is used for determining the objective parameter value as a first objective quality index of the first standard image if the similarity is smaller than a preset threshold value.

In some possible embodiments, the image sharpness description curve is a modulation function transfer curve, and the objective sharpness description curve obtaining unit is further configured to generate a description curve of the extreme diffraction lens formula according to the objective parameter value and the lens formula of the extreme diffraction lens; the objective parameter value represents the pixel resolution capability of the camera equipment; the description curve of the above-described extreme diffraction lens formula is determined as the above-described objective definition description curve.

In some possible embodiments, the first image sequence generating module is configured to obtain an image processing parameter for each scale value; processing the first standard image according to the image processing parameters to obtain a processed image; acquiring a second objective quality index of the processed image; determining a second subjective quality value corresponding to the second objective quality index according to the association relation; and if the second subjective quality value is equal to the scale value, determining the processed image as a first related image corresponding to the scale value.

In some possible embodiments, the first image sequence generating module is further configured to record a correspondence between the scale value and the image processing parameter.

In some possible embodiments, the apparatus is further configured to acquire a second standard image; acquiring the scale value sequence; processing the second standard image according to the corresponding relation between the scale values and the image processing parameters aiming at each scale value in the scale value sequence to obtain a second associated image corresponding to the scale value; generating a second image sequence according to a second associated image corresponding to each scale value in the scale value sequence; and generating a second image quality scale according to the scale value sequence and the second image sequence.

FIG. 18 shows a block diagram of an apparatus for evaluating image quality based on an image quality scale according to an embodiment of the present disclosure; as shown in fig. 18, the above apparatus includes:

the image to be evaluated acquiring module 10-1 is used for acquiring an image to be evaluated;

the image quality scale acquisition module 20-1 is used for acquiring an image quality scale;

a target image determining module 30-1, configured to determine a target image with the highest quality similarity to the image to be evaluated from among the plurality of images included in the image quality scale;

an evaluation result output module 40-1, configured to determine, based on a plurality of scale values included in the image quality scale, a target scale value corresponding to the target image as an evaluation result of the image to be evaluated; the image quality scale is obtained according to the method for generating the image quality scale shown in the embodiment of the present disclosure.

In some possible embodiments, the target image determining module 30-1 is further configured to display the image to be evaluated; displaying each image in the target image quality scale; and in response to an operation instruction of a user, determining the selected image in the target image quality scale, and taking the selected image as the target image.

In some embodiments, functions of or modules included in the apparatus provided in the embodiments of the present disclosure may be used to execute the method described in the above method embodiments, and specific implementations thereof may be as described in the above method embodiments, and for brevity, are not described herein again.

The embodiment of the present disclosure also provides a computer-readable storage medium, where at least one instruction or at least one program is stored in the computer-readable storage medium, and the at least one instruction or the at least one program is loaded by a processor and executed to implement the method. The computer readable storage medium may be a non-volatile computer readable storage medium.

An embodiment of the present disclosure further provides an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured as the method.

The electronic device may be provided as a terminal, server, or other form of device.

FIG. 19 shows a block diagram of an electronic device in accordance with an embodiment of the disclosure. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, or the like terminal.

Fig. 19, electronic device 800 may include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814, and communication component 816.

The processing component 802 generally controls overall operation of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing components 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store various types of data to support operations at the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The power supply component 806 provides power to the various components of the electronic device 800. The power components 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the electronic device 800.

The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and a user as described above. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of the touch or slide action but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the electronic device 800 is in an operation mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for the electronic device 800. For example, the sensor assembly 814 may detect an open/closed state of the electronic device 800, the relative positioning of components, such as a display and keypad of the electronic device 800, the sensor assembly 814 may also detect a change in position of the electronic device 800 or a component of the electronic device 800, the presence or absence of user contact with the electronic device 800, orientation or acceleration/deceleration of the electronic device 800, and a change in temperature of the electronic device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 may access a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G, 5G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the above-mentioned communication component 816 further comprises a Near Field Communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the electronic device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

In an exemplary embodiment, a non-transitory computer-readable storage medium, such as the memory 804, is also provided that includes computer program instructions executable by the processor 820 of the electronic device 800 to perform the above-described methods.

Fig. 20 shows a block diagram of another electronic device in accordance with an embodiment of the disclosure. For example, the electronic device 1900 may be provided as a server. In fig. 20, the electronic device 1900 includes a processing component 1922 further including one or more processors and memory resources, represented by memory 1932, for storing instructions, e.g., application programs, that are executable by the processing component 1922. The application programs stored in memory 1932 may include one or more modules that each correspond to a set of instructions. Further, the processing component 1922 is configured to execute instructions to perform the above-described method.

The electronic device 1900 may also include a power component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input/output (I/O) interface 1958. The electronic device 1900 may operate based on an operating system stored in memory 1932, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.

In an exemplary embodiment, a non-transitory computer readable storage medium, such as the memory 1932, is also provided that includes computer program instructions executable by the processing component 1922 of the electronic device 1900 to perform the above-described methods.

The present disclosure may be systems, methods, and/or computer program products. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied thereon for causing a processor to implement various aspects of the present disclosure.

The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.

The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.

The computer program instructions for carrying out operations of the present disclosure may be assembler instructions, instruction set architecture (isa) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, the electronic circuitry that can execute the computer-readable program instructions implements aspects of the present disclosure by utilizing the state information of the computer-readable program instructions to personalize the electronic circuitry, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA).

Various aspects of the present disclosure are described herein in terms of flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Having described embodiments of the present disclosure, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terms used herein were chosen in order to best explain the principles of the embodiments, the practical application, or technical improvements to the techniques in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method of generating an image quality scale, the method comprising:

acquiring a first standard image;

acquiring a first objective quality index of the first standard image;

determining a first subjective quality value corresponding to the first objective quality index according to the incidence relation between a preset objective quality index and a preset subjective quality value, and determining the first subjective quality value as a basic scale value;

generating a scale value sequence according to the basic scale value and a preset scale value generation rule, wherein the scale value sequence comprises a plurality of scale values;

acquiring a first associated image corresponding to each scale value, and generating a first image sequence, wherein for the first associated image corresponding to each scale value, a second subjective quality value of the first associated image is equal to the scale value;

and generating a first image quality scale according to the scale value sequence and the first image sequence.

2. The method according to claim 1, wherein the obtaining of the first objective quality indicator of the first standard image comprises:

obtaining objective parameter values, wherein the objective parameter values are used for determining the shape of an objective definition description curve;

obtaining the objective definition description curve according to the objective parameter value;

generating an image definition description curve corresponding to the first standard image according to the first standard image;

calculating the similarity between the objective definition description curve and the image definition description curve;

and if the similarity is smaller than a preset threshold value, determining the objective parameter value as a first objective quality index of the first standard image.

3. The method according to claim 2, wherein after said calculating the similarity of the objective sharpness profile to the image sharpness profile, the method further comprises:

and if the similarity is greater than or equal to the preset threshold value, adjusting the objective parameter value.

4. The method according to claim 2 or 3, wherein said deriving said objective sharpness description curve based on said objective parameter values comprises:

generating a description curve of the limit diffraction lens formula according to the objective parameter value and the lens formula of the limit diffraction lens; the objective parameter value represents the pixel resolution capability of the camera equipment;

determining a description curve of the extreme diffraction lens formula as the objective definition description curve.

5. The method according to any one of claims 1 to 4, wherein the obtaining of the first correlation image corresponding to each scale value comprises:

acquiring an image processing parameter for each scale value;

processing the first standard image according to the image processing parameters to obtain a processed image;

acquiring a second objective quality index of the processed image;

determining a second subjective quality value corresponding to the second objective quality index according to the incidence relation;

and if the second subjective quality value is equal to the scale value, determining the processed image as a first associated image corresponding to the scale value.

6. The method according to claim 5, wherein after said determining a second subjective quality value corresponding to the second objective quality indicator according to the correlation, the method further comprises:

and if the second subjective quality value of the processed image is not equal to the scale value, adjusting the image processing parameter.

7. The method according to claim 5 or 6, wherein after said determining said processed image as a first associated image corresponding to said scale value, said method further comprises:

and recording the corresponding relation between the scale value and the image processing parameter.

8. The method according to claim 7, wherein after said recording the correspondence of said scale values to said image processing parameters, the method further comprises:

acquiring a second standard image;

acquiring the scale value sequence;

processing the second standard image according to the corresponding relation between the scale value and the image processing parameter aiming at each scale value in the scale value sequence to obtain a second associated image corresponding to the scale value;

generating a second image sequence according to a second associated image corresponding to each scale value in the scale value sequence;

and generating a second image quality scale according to the scale value sequence and the second image sequence.

9. A method for evaluating image quality based on an image quality scale, the method comprising:

acquiring an image to be evaluated;

acquiring an image quality scale;

determining a target image with the highest quality similarity with the image to be evaluated from a plurality of images included by the image quality scale;

determining a target scale value corresponding to the target image as an evaluation result of the image to be evaluated based on a plurality of scale values included by the image quality scale;

wherein the image quality scale is obtained by the method for generating an image quality scale according to any one of claims 1 to 8.

10. The method according to claim 9, wherein the determining a target image with the highest quality similarity to the image to be evaluated from the plurality of images included in the image quality scale comprises:

displaying the image to be evaluated;

displaying each image in the target image quality scale;

and in response to an operation instruction of a user, determining a selected image in the target image quality scale, and taking the selected image as the target image.

11. An apparatus for generating an image quality scale, the apparatus comprising:

the first standard image acquisition module is used for acquiring a first standard image;

the objective quality index acquisition module is used for acquiring a first objective quality index of the first standard image;

the subjective quality value acquisition module is used for determining a first subjective quality value corresponding to the first objective quality index according to the incidence relation between a preset objective quality index and a preset subjective quality value, and determining the first subjective quality value as a basic scale value;

the scale value sequence generating module is used for generating a scale value sequence according to the basic scale value and a preset scale value generating rule, wherein the scale value sequence comprises a plurality of scale values;

a first image sequence generation module, configured to obtain a first associated image corresponding to each scale value, and generate a first image sequence, where for the first associated image corresponding to each scale value, a second subjective quality value of the first associated image is equal to the scale value;

and the first image quality scale generating module is used for generating a first image quality scale according to the scale value sequence and the first image sequence.

12. An apparatus for evaluating image quality based on an image quality scale, the apparatus comprising:

the image to be evaluated acquisition module is used for acquiring an image to be evaluated;

the image quality scale acquisition module is used for acquiring an image quality scale;

the target image determining module is used for determining a target image with the highest quality similarity with the image to be evaluated from a plurality of images included in the image quality scale;

the evaluation result output module is used for determining a target scale value corresponding to the target image as an evaluation result of the image to be evaluated based on a plurality of scale values included by the image quality scale;

13. A computer-readable storage medium, having at least one instruction or at least one program stored therein, which is loaded and executed by a processor to implement a method of generating an image quality scale according to any one of claims 1 to 8 or a method of evaluating image quality based on an image quality scale according to claim 9 or 10.

14. An electronic device comprising at least one processor, and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the at least one processor implements a method of generating an image quality scale according to any one of claims 1 to 8 or a method of evaluating image quality based on an image quality scale according to claim 9 or 10 by executing the instructions stored by the memory.